A5001426227- Landslides and related hazards
- Cryospheric studies and observations
- Text and Document Classification Technologies
- Face and Expression Recognition
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Anomaly Detection Techniques and Applications
- Fire effects on ecosystems
- Complex Network Analysis Techniques
- Advanced Graph Neural Networks
- Recommender Systems and Techniques
- Scheduling and Optimization Algorithms
- Evolutionary Algorithms and Applications
- Neural Networks and Applications
- Machine Learning in Bioinformatics
- Privacy, Security, and Data Protection
- Game Theory and Applications
- Human Pose and Action Recognition
- Flood Risk Assessment and Management
- Dam Engineering and Safety
- Digital Transformation in Industry
- Opinion Dynamics and Social Influence
- Yersinia bacterium, plague, ectoparasites research
- Big Data and Business Intelligence
- Blockchain Technology Applications and Security
- Privacy-Preserving Technologies in Data
Chengdu University of Technology
2018-2025
Ministry of Natural Resources
2023
University of Electronic Science and Technology of China
2017-2022
Earthquake-triggered landslides frequently occur in active mountain areas, which poses great threats to the safety of human lives and public infrastructures. Fast accurate mapping coseismic is important for earthquake disaster emergency rescue landslide risk analysis. Machine learning methods provide automatic solutions detection, are more efficient than manual mapping. Deep technologies attracting increasing interest detection. CNN one most widely used deep frameworks However, practice,...
Landslide detection and distribution mapping are essential components of geohazard prevention. For the extremely difficult problem automatic forested landslide detection, airborne remote sensing technologies, such as LiDAR optical cameras, can obtain more accurate monitoring data. In practice, however, data images treated independently. The complementary information from multiple sources has not been thoroughly investigated. To address this deficiency, we investigate how to use together...
ABSTRACT Detecting landslides is a critical challenge within the remote sensing fraternity, especially given need for timely and accurate hazard assessment. Traditional methods identifying from data are often manual or partially automated; however, with progress of computer vision technology, automated based on deep learning algorithms have gained significant attention. Furthermore, attention mechanisms, inspired by human visual structure, grown remarkably in various applications, including...
Landslides pose substantial risks to both local populations and critical infrastructure in high-risk areas. Numerous technologies have been developed monitor landslides, resulting a growing amount of landslide monitoring data, such as very high resolution remote sensing data in-situ data. These great potential for developing advanced machine learning models geohazard assessment. Privacy security issues are raising concerns, hindering the collection large datasets required powerful models....
Atmospheric effects are among the primary error sources affecting accuracy of interferometric synthetic aperture radar (InSAR). The topography-dependent atmospheric effect is particularly noteworthy in reservoir areas for landslide monitoring utilizing InSAR, which must be effectively corrected to complete InSAR high-accuracy measurement. This paper proposed a correction method based on Multi-Layer Perceptron (MLP) neural network model combined with topography and spatial data information....
Synthetic aperture radar interferometry (InSAR) has emerged as an effective technique for monitoring potentially unstable landslides and found widespread application. Nevertheless, in mountainous reservoir regions, the precision of time-series InSAR outcomes is often constrained by topography-dependent atmospheric delay (TDAD) effects. To address this limitation, we propose a novel method that integrates TDAD correction. This approach employs advanced deep learning algorithms to individually...
Landslide recognition is widely used in natural disaster risk management. Traditional landslide mainly conducted by geologists, which accurate but inefficient. This article introduces multiple instance learning (MIL) to perform automatic recognition. An end-to-end deep convolutional neural network proposed, referred as Multiple Instance Learning–based classification (MILL). First, MILL uses a large-scale remote sensing image dataset build pre-train networks for feature extraction. Second,...
Automated detection of landslides is an important part geohazard prevention. In dense vegetation covered area, identifying a challenging problem. Various types landslide monitoring technologies have generated heterogeneous data, such as optical imagery, SAR and LiDAR point clouds. Different methods their advantages drawbacks. An ideal model should utilize advantages. However, the complementary information multi-source data has not been fully understood. To deal with this problem, we study...
<title>Abstract</title> In deep neural network recommendation models, a common training method is to provide both positive and negative examples the model construct loss function, in order that can better learn useful information data because of increased distinction between examples. Due their focus on strong examples, traditional sampling methods tend select false samples, which leads overfitting, reduces generalization ability model, brings considerable extra computational overhead. For...